TY - JOUR
T1 - VIDOSAT
T2 - High-dimensional sparsifying transform learning for online video denoising
AU - Wen, Bihan
AU - Ravishankar, Saiprasad
AU - Bresler, Yoram
N1 - Funding Information:
Manuscript received October 2, 2017; revised June 2, 2018; accepted July 23, 2018. Date of publication August 16, 2018; date of current version December 3, 2018. This work was supported in part by the National Science Foundation (NSF) under Grant CCF-1320953. The work of S. Ravishankar was supported in part by the ONR Grant N00014-15-1-2141, in part by the DARPA Young Faculty Award D14AP00086, in part by ARO MURI under Grant W911NF-11-1-0391 and Grant 2015-05174-05, and in part by the UM-SJTU Seed Grant. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Gene Cheung. (Corresponding author: Bihan Wen.) B. Wen and Y. Bresler are with the Coordinated Science Laboratory, Department of Electrical and Computer Engineering, University of Illinois at Urbana–Champaign, Champaign, IL 61801 USA (e-mail: bwen3@illinois.edu; ybresler@illinois.edu).
Publisher Copyright:
© 1992-2012 IEEE.
PY - 2019/4
Y1 - 2019/4
N2 - Techniques exploiting the sparsity of images in a transform domain are effective for various applications in image and video processing. In particular, transform learning methods involve cheap computations and have been demonstrated to perform well in applications, such as image denoising and medical image reconstruction. Recently, we proposed methods for online learning of sparsifying transforms from streaming signals, which enjoy good convergence guarantees and involve lower computational costs than online synthesis dictionary learning. In this paper, we apply online transform learning to video denoising. We present a novel framework for online video denoising based on high-dimensional sparsifying transform learning for spatio-temporal patches. The patches are constructed either from corresponding 2D patches in successive frames or using an online block matching technique. The proposed online video denoising requires little memory and offers efficient processing. Numerical experiments evaluate the performance of the proposed video denoising algorithms on multiple video data sets. The proposed methods outperform several related and recent techniques, including denoising with 3D DCT, prior schemes based on dictionary learning, non-local means, background separation, and deep learning, as well as the popular VBM3D and VBM4D.
AB - Techniques exploiting the sparsity of images in a transform domain are effective for various applications in image and video processing. In particular, transform learning methods involve cheap computations and have been demonstrated to perform well in applications, such as image denoising and medical image reconstruction. Recently, we proposed methods for online learning of sparsifying transforms from streaming signals, which enjoy good convergence guarantees and involve lower computational costs than online synthesis dictionary learning. In this paper, we apply online transform learning to video denoising. We present a novel framework for online video denoising based on high-dimensional sparsifying transform learning for spatio-temporal patches. The patches are constructed either from corresponding 2D patches in successive frames or using an online block matching technique. The proposed online video denoising requires little memory and offers efficient processing. Numerical experiments evaluate the performance of the proposed video denoising algorithms on multiple video data sets. The proposed methods outperform several related and recent techniques, including denoising with 3D DCT, prior schemes based on dictionary learning, non-local means, background separation, and deep learning, as well as the popular VBM3D and VBM4D.
KW - Sparse representations
KW - big data
KW - data-driven techniques
KW - machine learning
KW - online learning
KW - sparsifying transforms
KW - video denoising
UR - http://www.scopus.com/inward/record.url?scp=85051820622&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051820622&partnerID=8YFLogxK
U2 - 10.1109/TIP.2018.2865684
DO - 10.1109/TIP.2018.2865684
M3 - Article
C2 - 30130189
AN - SCOPUS:85051820622
VL - 28
SP - 1691
EP - 1704
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
SN - 1057-7149
IS - 4
M1 - 8438535
ER -